首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0716118-133400


URN etd-0716118-133400 Statistics This thesis had been viewed 149 times. Download 0 times.
Author Chen-han Szu
Author's Email Address chszu717@gmail.com
Department Electrical Engineering
Year 2017 Semester 2
Degree Master Type of Document Master's Thesis
Language zh-TW.Big5 Chinese Page Count 29
Title Achieve Early Warning For Electrical Error By Deep Learning
Keyword
  • Deep learning
  • Neural Network
  • Backpropagation
  • Long Short-Term Memory
  • Smart Electricity Grid
  • Power Systems
  • Electrical Error
  • Electrical Error
  • Power Systems
  • Smart Electricity Grid
  • Long Short-Term Memory
  • Backpropagation
  • Neural Network
  • Deep learning
  • Abstract Science and technology have improved our living standard, the electrical safety has been forgotten easily when the amount of electric power set a new high year by year. According to national fire analysis report made by National Fire Agency, Ministry of the Interior “Electrical fire account for 32.8% of the year 2016, and made 49 people died.” Illegal structures, overloaded power strip, decoration with inflammable materials, disrepair for long time, make potential hazards to the electrical fire.
      Electrical error from live wire often leads to voltage drop and overheating of wire and device. The neutral wire error makes imbalance phases from wire, which let voltage drop from heavy load and voltage rise from light load. These situation may show a big difference from the characteristics as usual.
      This research try to find a positive way of early warning utilize Backpropagation Neural Networks and Long Short-Term Memory Neural Networks for deep learning, which can protect loss of life and property from electrical error, which would complete smart electricity grid for a more stable power system.
    Advisor Committee
  • Chau-Yun Hsu - advisor
  • An-Yi Chen - co-chair
  • Wen-Chen Chu - co-chair
  • Files indicate access worldwide
    Date of Defense 2018-07-02 Date of Submission 2018-07-16


    Browse | Search All Available ETDs